diff options
Diffstat (limited to 'src/include/port/pg_bitutils.h')
| -rw-r--r-- | src/include/port/pg_bitutils.h | 38 |
1 files changed, 36 insertions, 2 deletions
diff --git a/src/include/port/pg_bitutils.h b/src/include/port/pg_bitutils.h index 53e52397170..de480da71e1 100644 --- a/src/include/port/pg_bitutils.h +++ b/src/include/port/pg_bitutils.h @@ -302,17 +302,51 @@ pg_ceil_log2_64(uint64 num) /* Attempt to use the POPCNT instruction, but perform a runtime check first */ extern PGDLLIMPORT int (*pg_popcount32) (uint32 word); extern PGDLLIMPORT int (*pg_popcount64) (uint64 word); -extern PGDLLIMPORT uint64 (*pg_popcount) (const char *buf, int bytes); +extern PGDLLIMPORT uint64 (*pg_popcount_optimized) (const char *buf, int bytes); #else /* Use a portable implementation -- no need for a function pointer. */ extern int pg_popcount32(uint32 word); extern int pg_popcount64(uint64 word); -extern uint64 pg_popcount(const char *buf, int bytes); +extern uint64 pg_popcount_optimized(const char *buf, int bytes); #endif /* TRY_POPCNT_FAST */ /* + * Returns the number of 1-bits in buf. + * + * If there aren't many bytes to process, the function call overhead of the + * optimized versions isn't worth taking, so we inline a loop that consults + * pg_number_of_ones in that case. If there are many bytes to process, we + * accept the function call overhead because the optimized versions are likely + * to be faster. + */ +static inline uint64 +pg_popcount(const char *buf, int bytes) +{ + /* + * We set the threshold to the point at which we'll first use special + * instructions in the optimized version. + */ +#if SIZEOF_VOID_P >= 8 + int threshold = 8; +#else + int threshold = 4; +#endif + + if (bytes < threshold) + { + uint64 popcnt = 0; + + while (bytes--) + popcnt += pg_number_of_ones[(unsigned char) *buf++]; + return popcnt; + } + + return pg_popcount_optimized(buf, bytes); +} + +/* * Rotate the bits of "word" to the right/left by n bits. */ static inline uint32 |